Cargando…

Latent Patient Cluster Discovery for Robust Future Forecasting and New-Patient Generalization

Commonly referred to as predictive modeling, the use of machine learning and statistical methods to improve healthcare outcomes has recently gained traction in biomedical informatics research. Given the vast opportunities enabled by large Electronic Health Records (EHR) data and powerful resources f...

Descripción completa

Detalles Bibliográficos
Autores principales: Qian, Ting, Masino, Aaron J.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2016
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5026362/
https://www.ncbi.nlm.nih.gov/pubmed/27636203
http://dx.doi.org/10.1371/journal.pone.0162812
_version_ 1782454117179850752
author Qian, Ting
Masino, Aaron J.
author_facet Qian, Ting
Masino, Aaron J.
author_sort Qian, Ting
collection PubMed
description Commonly referred to as predictive modeling, the use of machine learning and statistical methods to improve healthcare outcomes has recently gained traction in biomedical informatics research. Given the vast opportunities enabled by large Electronic Health Records (EHR) data and powerful resources for conducting predictive modeling, we argue that it is yet crucial to first carefully examine the prediction task and then choose predictive methods accordingly. Specifically, we argue that there are at least three distinct prediction tasks that are often conflated in biomedical research: 1) data imputation, where a model fills in the missing values in a dataset, 2) future forecasting, where a model projects the development of a medical condition for a known patient based on existing observations, and 3) new-patient generalization, where a model transfers the knowledge learned from previously observed patients to newly encountered ones. Importantly, the latter two tasks—future forecasting and new-patient generalizations—tend to be more difficult than data imputation as they require predictions to be made on potentially out-of-sample data (i.e., data following a different predictable pattern from what has been learned by the model). Using hearing loss progression as an example, we investigate three regression models and show that the modeling of latent clusters is a robust method for addressing the more challenging prediction scenarios. Overall, our findings suggest that there exist significant differences between various kinds of prediction tasks and that it is important to evaluate the merits of a predictive model relative to the specific purpose of a prediction task.
format Online
Article
Text
id pubmed-5026362
institution National Center for Biotechnology Information
language English
publishDate 2016
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-50263622016-09-27 Latent Patient Cluster Discovery for Robust Future Forecasting and New-Patient Generalization Qian, Ting Masino, Aaron J. PLoS One Research Article Commonly referred to as predictive modeling, the use of machine learning and statistical methods to improve healthcare outcomes has recently gained traction in biomedical informatics research. Given the vast opportunities enabled by large Electronic Health Records (EHR) data and powerful resources for conducting predictive modeling, we argue that it is yet crucial to first carefully examine the prediction task and then choose predictive methods accordingly. Specifically, we argue that there are at least three distinct prediction tasks that are often conflated in biomedical research: 1) data imputation, where a model fills in the missing values in a dataset, 2) future forecasting, where a model projects the development of a medical condition for a known patient based on existing observations, and 3) new-patient generalization, where a model transfers the knowledge learned from previously observed patients to newly encountered ones. Importantly, the latter two tasks—future forecasting and new-patient generalizations—tend to be more difficult than data imputation as they require predictions to be made on potentially out-of-sample data (i.e., data following a different predictable pattern from what has been learned by the model). Using hearing loss progression as an example, we investigate three regression models and show that the modeling of latent clusters is a robust method for addressing the more challenging prediction scenarios. Overall, our findings suggest that there exist significant differences between various kinds of prediction tasks and that it is important to evaluate the merits of a predictive model relative to the specific purpose of a prediction task. Public Library of Science 2016-09-16 /pmc/articles/PMC5026362/ /pubmed/27636203 http://dx.doi.org/10.1371/journal.pone.0162812 Text en © 2016 Qian, Masino http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Qian, Ting
Masino, Aaron J.
Latent Patient Cluster Discovery for Robust Future Forecasting and New-Patient Generalization
title Latent Patient Cluster Discovery for Robust Future Forecasting and New-Patient Generalization
title_full Latent Patient Cluster Discovery for Robust Future Forecasting and New-Patient Generalization
title_fullStr Latent Patient Cluster Discovery for Robust Future Forecasting and New-Patient Generalization
title_full_unstemmed Latent Patient Cluster Discovery for Robust Future Forecasting and New-Patient Generalization
title_short Latent Patient Cluster Discovery for Robust Future Forecasting and New-Patient Generalization
title_sort latent patient cluster discovery for robust future forecasting and new-patient generalization
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5026362/
https://www.ncbi.nlm.nih.gov/pubmed/27636203
http://dx.doi.org/10.1371/journal.pone.0162812
work_keys_str_mv AT qianting latentpatientclusterdiscoveryforrobustfutureforecastingandnewpatientgeneralization
AT masinoaaronj latentpatientclusterdiscoveryforrobustfutureforecastingandnewpatientgeneralization